Filters








50,768 Hits in 2.8 sec

The collective memory of amnesic processes

Rachid Guerraoui, Ron R. Levy, Bastian Pochon, Jim Pugh
2008 ACM Transactions on Algorithms  
This paper considers the problem of robustly emulating a shared atomic memory over a distributed message passing system where processes can fail by crashing and possibly recover.  ...  The algorithm is instantiated for various settings according to whether processes have access to local stable storage, and whether, in every execution of the algorithm, a sufficient number of processes  ...  Proof: Line 2 of Figure 7 with stable storage and line 2 of Figure 8 without. 5 2.  ... 
doi:10.1145/1328911.1328923 fatcat:mcewbmotcveyngscozbidhmquy

Concurrent compacting garbage collection of a persistent heap

James O'Toole, Scott Nettles, David Gifford
1993 Proceedings of the fourteenth ACM symposium on Operating systems principles - SOSP '93  
When write operations are committed they are preserved in stable storage and survive system failures.  ...  The results suggest that replicating garbage collection offers a flexible and efficient way to provide automatic storage management in transaction systems, object-oriented databases and persistent programming  ...  Thus a slow stable storage medium can be used for to-space without slowing the garbage collector.  ... 
doi:10.1145/168619.168632 dblp:conf/sosp/OTooleNG93 fatcat:v5usd3unqvesde7eaexq76ojr4

Robust emulations of shared memory in a crash-recovery model

R. Guerraoui, R.R. Levy
2004 24th International Conference on Distributed Computing Systems, 2004. Proceedings.  
Index Terms-asynchronous distributed system, message passing, shared memory, crash-recovery, atomicity, logging, complexity, lower bound, optimality, stable storage.  ...  exchange messages to synchronize their read and write operations and (b) log key information on their local stable storage.  ...  Every process has a volatile and a stable storage. If it crashes and recovers, the process loses the content of its volatile storage but not the content of its stable storage.  ... 
doi:10.1109/icdcs.2004.1281605 dblp:conf/icdcs/GuerraouiL04 fatcat:rlry2xgs4nhu5no57zfdsujhi4

Transactions

Alfred Z. Spector, Peter M. Schwarz
1983 ACM SIGOPS Operating Systems Review  
General distributed systems, however, will use new types of low-latency stable storage, and very efficient communication is likely to be important.  ...  In a system allowing general shared abstract types, it is more difficult to decide which operations should be permanent or failure-atomic and which should not.  ...  Stable processors that recover from crashes can be built using stable storage to save processor state.  ... 
doi:10.1145/1041478.1041481 fatcat:p5movi7acnc25g3q6f7pzcaho4

Transparent optimistic rollback recovery

David B. Johnson, Willy Zwaenepoel
1990 Proceedings of the 4th workshop on ACM SIGOPS European workshop - EW 4  
With rollback recovery, information saved on stable storage during failure-free execution allows certain states of each process to be recovered after a failure.  ...  As a simple example, if the shared memory system knows that a particular object is "read-only," accesses to it need not be logged.  ... 
doi:10.1145/504136.504152 dblp:conf/sigopsE/JohnsonZ90 fatcat:47yt5il4u5b6ni62leoxefewxu

Transparent optimistic rollback recovery

David B. Johnson, Willy Zwaenepoel
1991 ACM SIGOPS Operating Systems Review  
With rollback recovery, information saved on stable storage during failure-free execution allows certain states of each process to be recovered after a failure.  ...  As a simple example, if the shared memory system knows that a particular object is "read-only," accesses to it need not be logged.  ... 
doi:10.1145/122120.122132 fatcat:nnpsbbzqfrg27gvcrr6m7pcyle

Reliable object storage to support atomic actions

Brian M. Oki, Barbara H. Liskov, Robert W. Scheifler
1985 ACM SIGOPS Operating Systems Review  
When resilient objects are modified, they are automatically copied by the Argus implementation to stable storage, storage that with very high probability does not lose information.  ...  This paper presents a method for implementing resilient objects, using a log-based mechanism to organize the information on stable storage.  ...  As an action gets ready to commit, the new object versions are.written to stable storage without destroying existing versions.  ... 
doi:10.1145/323627.323642 fatcat:kgb6jznp7bfezcptzzbjsjooii

Bounding Recovery Time in Rollback-Recovery Protocol for Mobile Systems Preserving Session Guarantees [chapter]

Jerzy Brzeziński, Anna Kobusińska, Jacek Kobusiński
2006 Lecture Notes in Computer Science  
Operations performed on shared objects are divided into reads and writes, denoted respectively by r and w. A read does not change states of the shared objects, while a write does.  ...  The system consists of a number of servers holding a full copy of shared objects and clients running applications that access these objects (see Fig. 1 ).  ... 
doi:10.1007/11773887_15 fatcat:ij4cupx5fzekhaphrxkdpdfcz4

Experience with modularity in consul

Shivakant Mishra, Larry L. Peterson, Richard D. Schlichting
1993 Software, Practice & Experience  
Issues that are addressed include deciding how the system is divided into various modules, dealing with problems that result when protocols are combined, and ensuring that the underlying object infrastructure  ...  is most affected by dependencies between modules, both direct dependencies caused by one module explicitly using another's operation and indirect dependencies where one module is affected by another without  ...  Thirdly, fault-tolerant protocols depend on a stable storage facility to recover after a processor failure.  ... 
doi:10.1002/spe.4380231002 fatcat:kvxszigczfeitcpuf4bzogvsyi

Rollback-Recovery Protocol Guarantying MR Session Guarantee in Distributed Systems with Mobile Clients [chapter]

Jerzy Brzeziński, Anna Kobusińska, Michał Szychowiak
2006 Lecture Notes in Computer Science  
The storage replicated by servers does not imply any particular data model or organization. Operations performed on shared objects are basically divided into reads and writes.  ...  To access the shared object, clients select a single server and send a direct request to this server.  ... 
doi:10.1007/11823285_55 fatcat:edomftt55bas3aqwfviwe3i2me

Efficient optimistic concurrency control using loosely synchronized clocks

Atul Adya, Robert Gruber, Barbara Liskov, Umesh Maheshwari
1995 SIGMOD record  
This paper describes an efficient optimistic concurrency control scheme for use in distributed database systems in which objects are cached and manipulated at client machines while persistent storage and  ...  that has low in-memory space overhead and no per-object disk overhead.  ...  The straightforward way to ensure this would be to log the validation information (VQ and threshold) on stable storage, so that it can be recovered after a crash.  ... 
doi:10.1145/568271.223787 fatcat:neificuocbcajbpylw7uafwj5a

Efficient optimistic concurrency control using loosely synchronized clocks

Atul Adya, Robert Gruber, Barbara Liskov, Umesh Maheshwari
1995 Proceedings of the 1995 ACM SIGMOD international conference on Management of data - SIGMOD '95  
This paper describes an efficient optimistic concurrency control scheme for use in distributed database systems in which objects are cached and manipulated at client machines while persistent storage and  ...  that has low in-memory space overhead and no per-object disk overhead.  ...  The straightforward way to ensure this would be to log the validation information (VQ and threshold) on stable storage, so that it can be recovered after a crash.  ... 
doi:10.1145/223784.223787 dblp:conf/sigmod/AdyaGLM95 fatcat:lifnzw47e5hjbefuyfi7lpxhwq

Transparent Orthogonal Checkpointing through User-Level Pagers [chapter]

Espen Skoglund, Christian Ceelen, Jochen Liedtke
2001 Lecture Notes in Computer Science  
storage.  ...  Not only are all data objects made persistent. Threads and tasks are also treated as normal data objects, making the threads and tasks persistent between system restarts.  ...  The checkpointer pickles the remaining parts of the objects and saves them to stable storage together with the memoryimages of the tasks.  ... 
doi:10.1007/3-540-45498-5_18 fatcat:rb7i5oy5tvhkpn3fop755fdwse

POTSHARDS—a secure, recoverable, long-term archival storage system

Mark W. Storer, Kevin M. Greenan, Ethan L. Miller, Kaladhar Voruganti
2009 ACM Transactions on Storage  
To address these concerns, we have developed POTSHARDS, an archival storage system that provides long-term security for data with very long lifetimes without using encryption.  ...  Secrecy is achieved by using unconditionally secure secret splitting and spreading the resulting shares across separately managed archives.  ...  ACKNOWLEDGMENTS We would like to thank our colleagues in the Storage Systems Research Center (SSRC) who provided valuable feedback on the ideas in this article.  ... 
doi:10.1145/1534912.1534914 fatcat:jvezhkkqkbeqzo6g27i4kz2xra

Fatman

An Qin, Dianming Hu, Jun Liu, Wenjun Yang, Dai Tan
2014 Proceedings of the VLDB Endowment  
Two major concerned issues of the system design are maximizing the resource utilization of volunteer nodes without violating Service Level Objectives (SLOs) and minimizing the cost without reducing the  ...  The system realizes an efficient storage quota consolidation by strong isolation and budget limitation, to maximally support resources contribution without any degradation on host-level SLOs.  ...  To smooth resource utilization without losing availability, assumptions are pre-required in some systems to determine when data can be recovered and how to be recovered [5] .  ... 
doi:10.14778/2733004.2733078 fatcat:7pnkj34lgnfhxcqssoxgq4iq4i
« Previous Showing results 1 — 15 out of 50,768 results